Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45097
    Prev
    Next
    INDEX
    Explanations

    marker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    税
    -0.09
     Taxes
    -0.09
    部门
    -0.09
     taxes
    -0.09
     taxe
    -0.09
     departamentos
    -0.08
     جهود
    -0.08
     Departments
    -0.08
     বিভাগের
    -0.08
    _tax
    -0.08
    POSITIVE LOGITS
     linestyle
    0.09
    -equipped
    0.08
     che
    0.08
     접
    0.08
     versehen
    0.07
     jedem
    0.07
    .scatter
    0.07
    .symbol
    0.07
    Scatter
    0.07
     alloys
    0.07
    Activations Density 0.002%

    No Known Activations